Predictive fault detection and resolution using YOLOv8 segmentation model: A comprehensive study on hotspot faults and generalization challenges in computer vision
Küçük Resim Yok
Tarih
2024-12-01
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Ain Shams University
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
Photovoltaic systems are considered the cornerstone of renewable energy, with rapidly increasing use and large-scale fields, there are significant limitations that affect their efficiency. This study presents the imperative necessity of promptly predicting failures to mitigate their adverse effects on performance with photovoltaic systems. Through an exploration of the most prevalent faults, their impacts, and cutting-edge solutions, this research contributes to the understanding and management of system failures. Furthermore, the study implements the YOLOv8 segmentation model to detect a specific type of fault known as a hotspot fault. The findings include a comprehensive examination of the results, incorporating data augmentation techniques, and assessing their influence on the overarching challenge of generalization in computer vision. This investigation not only enriches the discourse surrounding fault prediction but also offers insights into enhancing the robustness and reliability of fault detection methodologies.
Açıklama
Anahtar Kelimeler
Data Augmentation, Generalization, Hotspot Failure, Photovoltaic, Renewable Energy, YOLOv8 Segmentation
Kaynak
Ain Shams Engineering Journal
WoS Q Değeri
Scopus Q Değeri
Q1
Cilt
15
Sayı
12
